ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

memoclaw

Memory-as-a-Service for AI agents. Store and recall memories with semantic vector search. 100 free calls per wallet, then x402 micropayments. Your wallet address is your identity.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/anajuliabit/memoclaw
Or

What This Skill Does

MemoClaw provides persistent, semantic memory capabilities for AI agents, acting as a Memory-as-a-Service layer. It allows agents to store facts, decisions, observations, and project-specific data that survive across different execution sessions. By leveraging vector embeddings, the skill enables agents to recall relevant context using natural language queries rather than simple keyword matching. With an identity-based system tied directly to your cryptocurrency wallet address, there is no need for traditional API keys or registration hurdles.

Installation

To integrate MemoClaw into your environment, follow these steps:

  1. Ensure Node.js is installed.
  2. Run npm install -g memoclaw to add the CLI to your system path.
  3. Run memoclaw init to configure your wallet. This process creates the necessary cryptographic identity required to sign requests.
  4. Set the MEMOCLAW_PRIVATE_KEY environment variable in your terminal session to authorize the skill for autonomous operations.
  5. Finally, execute clawhub install openclaw/skills/skills/anajuliabit/memoclaw to register the skill within your OpenClaw agent workflow.

Use Cases

  • Project Continuity: Save research notes, code snippets, or user preferences to ensure your agent stays informed across long-running tasks.
  • Decision Auditing: Log critical decision-making processes under the 'decision' memory type to allow for future review or correction.
  • Personalized Agent Behavior: Store 'preference' type memories to customize how your agent interacts with specific inputs or stylistic requirements.
  • Knowledge Retrieval: Use the 'context' command to aggregate the most relevant memories for an LLM prompt, improving response accuracy.

Example Prompts

  1. "@memoclaw store 'User prefers concise responses without markdown tables' --memory-type preference"
  2. "@memoclaw recall 'what was the deadline discussed for the project migration?' --limit 3"
  3. "@memoclaw context 'Provide a summary of all project requirements saved last week' --limit 10"

Tips & Limitations

  • Cost Management: You receive 100 free API calls per wallet. Monitor your usage with memoclaw status. After the free tier is exhausted, ensure you have USDC on the Base network to avoid service interruptions.
  • Security: Always use a dedicated wallet for your AI agent that does not hold significant assets. Secure your private key carefully using environment variables.
  • Data Types: Choose your memory type carefully (correction, preference, decision, project, observation, general) as this helps with semantic filtering in advanced workflows.

Metadata

Stars4473
Views1
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-anajuliabit-memoclaw": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#memory#vector-database#ai-agents#base#persistence
Safety Score: 4/5

Flags: network-access, file-read, external-api